CVE-2026-0755

gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability. The specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783.

gemini-mcp-tool execAsync Command Injection Remote Code Execution Vulnerability. This vulnerability allows remote attackers to execute arbitrary code on affected installations of gemini-mcp-tool. Authentication is not required to exploit this vulnerability. The specific flaw exists within the implementation of the execAsync method. The issue results from the lack of proper validation of a user-supplied string before using it to execute a system call. An attacker can leverage this vulnerability to execute code in the context of the service account. Was ZDI-CAN-27783.

Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/id_rsa, @../../secret). On Windows, unquoted cmd.exe metacharacters could break out into OS command injection. Fix (1.1.6): removed the broken shell:false double-quote wrapping; added assertSafeFileReferences() to contain @file refs to the working directory; hardened Windows cmd.exe argument quoting.

Vulnerabilidad de inyección de comandos y ejecución remota de código en gemini-mcp-tool execAsync. Esta vulnerabilidad permite a atacantes remotos ejecutar código arbitrario en instalaciones afectadas de gemini-mcp-tool. No se requiere autenticación para explotar esta vulnerabilidad. La falla específica existe dentro de la implementación del método execAsync. El problema resulta de la falta de validación adecuada de una cadena proporcionada por el usuario antes de usarla para ejecutar una llamada al sistema. Un atacante puede aprovechar esta vulnerabilidad para ejecutar código en el contexto de la cuenta de servicio. Fue ZDI-CAN-27783.